[Tea Talk] Isabela Albuquerque (INRS) Fri February 1 2019 10h30 Mila Auditorium
This week we have Isabela Albuquerque from INRS giving a talk on Multi-objective training of Generative Adversarial Networks with multiple discriminators at 10h30 in room Mila Auditorium. Will this talk be streamed <https://mila.bluejeans.com/809027115/webrtc>? yes PS : Slides and recordings of previous talks are available at :https://sites.google.com/lisa.iro.umontreal.ca/tea-talk-recordings/home?auth... <https://sites.google.com/lisa.iro.umontreal.ca/tea-talk-recordings/home?authuser=0> See you there! Pablo, Sai and Rim TITLE Multi-objective training of Generative Adversarial Networks with multiple discriminators ABSTRACT Recent literature has demonstrated promising results for training Generative Adversarial Networks by employing a set of discriminators, in contrast to the traditional game involving one generator against a single adversary. Such methods perform single-objective optimization on some simple consolidation of the losses, e.g. an average. In this work, we revisit the multiple-discriminator setting by framing the simultaneous minimization of losses provided by different models as a multi-objective optimization problem. Specifically, we evaluate the performance of multiple gradient descent and the hypervolume maximization algorithm on a number of different datasets. Moreover, we argue that the previously proposed methods and hypervolume maximization can all be seen as variations of multiple gradient descent in which the update direction can be computed efficiently. Our results indicate that hypervolume maximization presents a better compromise between sample quality and computational cost than previous methods. BIO Isabela Albuquerque is a PhD candidate at the Institut National de la Recherche Scientifique (INRS), Université du Québec. Her main research interests are machine learning and cognitive neuroscience. The primary goal of her current research is improving the generalization across different individuals of electroencephalogram-based mental workload models. Prior to joining INRS, she received a Bachelor's degree in Electrical Engineering from the Federal University of Pernambuco and a Master's degree in Computer Engineering from the University of Pernambuco, both in Recife, Brazil.
Reminder : this happens in 30 minutes!
On Jan 28, 2019, at 12:36 PM, Rim Assouel <rim.assouel@gmail.com> wrote:
This week we have Isabela Albuquerque from INRS giving a talk on Multi-objective training of Generative Adversarial Networks with multiple discriminators at 10h30 in room Mila Auditorium.
Will this talk be streamed <https://mila.bluejeans.com/809027115/webrtc>? yes
PS : Slides and recordings of previous talks are available at :https://sites.google.com/lisa.iro.umontreal.ca/tea-talk-recordings/home?auth... <https://sites.google.com/lisa.iro.umontreal.ca/tea-talk-recordings/home?authuser=0>
See you there! Pablo, Sai and Rim
TITLE Multi-objective training of Generative Adversarial Networks with multiple discriminators
ABSTRACT Recent literature has demonstrated promising results for training Generative Adversarial Networks by employing a set of discriminators, in contrast to the traditional game involving one generator against a single adversary. Such methods perform single-objective optimization on some simple consolidation of the losses, e.g. an average. In this work, we revisit the multiple-discriminator setting by framing the simultaneous minimization of losses provided by different models as a multi-objective optimization problem. Specifically, we evaluate the performance of multiple gradient descent and the hypervolume maximization algorithm on a number of different datasets. Moreover, we argue that the previously proposed methods and hypervolume maximization can all be seen as variations of multiple gradient descent in which the update direction can be computed efficiently. Our results indicate that hypervolume maximization presents a better compromise between sample quality and computational cost than previous methods.
BIO Isabela Albuquerque is a PhD candidate at the Institut National de la Recherche Scientifique (INRS), Université du Québec. Her main research interests are machine learning and cognitive neuroscience. The primary goal of her current research is improving the generalization across different individuals of electroencephalogram-based mental workload models. Prior to joining INRS, she received a Bachelor's degree in Electrical Engineering from the Federal University of Pernambuco and a Master's degree in Computer Engineering from the University of Pernambuco, both in Recife, Brazil.
The talk is going to be streamed at https://mila.bluejeans.com/4862024040/webrtc <https://mila.bluejeans.com/4862024040/webrtc> On Fri, Feb 1, 2019 at 9:57 AM Rim Assouel <rim.assouel@gmail.com> wrote:
Reminder : this happens in 30 minutes!
On Jan 28, 2019, at 12:36 PM, Rim Assouel <rim.assouel@gmail.com> wrote:
This week we have * Isabela Albuquerque* from * INRS * giving a talk on * Multi-objective training of Generative Adversarial Networks with multiple discriminators* at * 10h30* in room * Mila Auditorium*.
Will this talk be streamed <https://mila.bluejeans.com/809027115/webrtc>? yes
PS : Slides and recordings of previous talks are available at : https://sites.google.com/lisa.iro.umontreal.ca/tea-talk-recordings/home?auth...
See you there! Pablo, Sai and Rim
*TITLE* Multi-objective training of Generative Adversarial Networks with multiple discriminators
*ABSTRACT* Recent literature has demonstrated promising results for training Generative Adversarial Networks by employing a set of discriminators, in contrast to the traditional game involving one generator against a single adversary. Such methods perform single-objective optimization on some simple consolidation of the losses, e.g. an average. In this work, we revisit the multiple-discriminator setting by framing the simultaneous minimization of losses provided by different models as a multi-objective optimization problem. Specifically, we evaluate the performance of multiple gradient descent and the hypervolume maximization algorithm on a number of different datasets. Moreover, we argue that the previously proposed methods and hypervolume maximization can all be seen as variations of multiple gradient descent in which the update direction can be computed efficiently. Our results indicate that hypervolume maximization presents a better compromise between sample quality and computational cost than previous methods.
*BIO* Isabela Albuquerque is a PhD candidate at the Institut National de la Recherche Scientifique (INRS), Université du Québec. Her main research interests are machine learning and cognitive neuroscience. The primary goal of her current research is improving the generalization across different individuals of electroencephalogram-based mental workload models. Prior to joining INRS, she received a Bachelor's degree in Electrical Engineering from the Federal University of Pernambuco and a Master's degree in Computer Engineering from the University of Pernambuco, both in Recife, Brazil.
-- You received this message because you are subscribed to the Google Groups "MILA Tous" group. To unsubscribe from this group and stop receiving emails from it, send an email to mila-tous+unsubscribe@mila.quebec.
participants (2)
-
Pablo Fonseca -
Rim Assouel